Closed aparico closed 3 years ago
I have also tried doing it locally.
Here are the results:
ROI initialized on [(144, 453), (1381, 440)]
Traceback (most recent call last):
File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 497, in _import_graph_def_internal
graph._c_graph, serialized, options) # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.InvalidArgumentError: NodeDef mentions attr 'exponential_avg_factor' not in Op<name=FusedBatchNormV3; signature=x:T, scale:U, offset:U, mean:U, variance:U -> y:T, batch_mean:U, batch_variance:U, reserve_space_1:U, reserve_space_2:U, reserve_space_3:U; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT]; attr=U:type,allowed=[DT_FLOAT]; attr=epsilon:float,default=0.0001; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=is_training:bool,default=true>; NodeDef: {{node FusedBatchNormV3}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "detectvideo_counter.py", line 208, in <module>
app.run(main)
File "C:\Python37\lib\site-packages\absl\app.py", line 303, in run
_run_main(main, args)
File "C:\Python37\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "detectvideo_counter.py", line 77, in main
saved_model_loaded = tf.saved_model.load(FLAGS.weights, tags=[tag_constants.SERVING])
File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 528, in load
return load_internal(export_dir, tags)
File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 552, in load_internal
export_dir)
File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 114, in __init__
meta_graph.graph_def.library))
File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\function_deserialization.py", line 312, in load_function_def_library
func_graph = function_def_lib.function_def_to_graph(copy)
File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\function_def_to_graph.py", line 63, in function_def_to_graph
importer.import_graph_def_for_function(graph_def, name="")
File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 412, in import_graph_def_for_function
graph_def, validate_colocation_constraints=False, name=name)
File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 501, in _import_graph_def_internal
raise ValueError(str(e))
ValueError: NodeDef mentions attr 'exponential_avg_factor' not in Op<name=FusedBatchNormV3; signature=x:T, scale:U, offset:U, mean:U, variance:U -> y:T, batch_mean:U, batch_variance:U, reserve_space_1:U, reserve_space_2:U, reserve_space_3:U; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT]; attr=U:type,allowed=[DT_FLOAT]; attr=epsilon:float,default=0.0001; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=is_training:bool,default=true>; NodeDef: {{node FusedBatchNormV3}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
I tried to run this command in Colab:
! python detectvideo_counter.py --weights ./checkpoints/yolov4-416/ --size 608 --video {path_video} --score 0.9
This is the result:
2020-12-15 10:16:28.871548: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-12-15 10:16:30.485081: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1 2020-12-15 10:16:30.500551: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.501442: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:00:04.0 name: Tesla P100-PCIE-16GB computeCapability: 6.0 coreClock: 1.3285GHz coreCount: 56 deviceMemorySize: 15.90GiB deviceMemoryBandwidth: 681.88GiB/s 2020-12-15 10:16:30.501492: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-12-15 10:16:30.503429: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2020-12-15 10:16:30.505250: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2020-12-15 10:16:30.505727: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2020-12-15 10:16:30.507646: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2020-12-15 10:16:30.508808: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2020-12-15 10:16:30.512795: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2020-12-15 10:16:30.512906: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.513710: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.514514: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2020-12-15 10:16:30.542917: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2199995000 Hz 2020-12-15 10:16:30.543133: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5e963d0 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2020-12-15 10:16:30.543165: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2020-12-15 10:16:30.638624: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.639616: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5f120a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2020-12-15 10:16:30.639655: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Tesla P100-PCIE-16GB, Compute Capability 6.0 2020-12-15 10:16:30.639885: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.640702: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:00:04.0 name: Tesla P100-PCIE-16GB computeCapability: 6.0 coreClock: 1.3285GHz coreCount: 56 deviceMemorySize: 15.90GiB deviceMemoryBandwidth: 681.88GiB/s 2020-12-15 10:16:30.640761: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-12-15 10:16:30.640821: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2020-12-15 10:16:30.640880: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2020-12-15 10:16:30.640973: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2020-12-15 10:16:30.641017: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2020-12-15 10:16:30.641057: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2020-12-15 10:16:30.641096: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2020-12-15 10:16:30.641228: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.642158: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:30.643124: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2020-12-15 10:16:30.643184: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-12-15 10:16:31.057796: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix: 2020-12-15 10:16:31.057858: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] 0 2020-12-15 10:16:31.057876: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0: N 2020-12-15 10:16:31.058130: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.059104: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.060054: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14968 MB memory) -> physical GPU (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0) /usr/local/lib/python3.6/dist-packages/sklearn/utils/linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead. FutureWarning) 2020-12-15 10:16:31.598154: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.599049: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:00:04.0 name: Tesla P100-PCIE-16GB computeCapability: 6.0 coreClock: 1.3285GHz coreCount: 56 deviceMemorySize: 15.90GiB deviceMemoryBandwidth: 681.88GiB/s 2020-12-15 10:16:31.599103: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-12-15 10:16:31.599166: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2020-12-15 10:16:31.599211: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2020-12-15 10:16:31.599250: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2020-12-15 10:16:31.599285: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2020-12-15 10:16:31.599319: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2020-12-15 10:16:31.599354: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2020-12-15 10:16:31.599459: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.600366: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.601197: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2020-12-15 10:16:31.601248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix: 2020-12-15 10:16:31.601270: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] 0 2020-12-15 10:16:31.601283: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0: N 2020-12-15 10:16:31.601396: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.602222: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-15 10:16:31.603008: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14968 MB memory) -> physical GPU (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0) Video from: data/test.mp4 : cannot connect to X server
It's not possible in Colab because the code opens a separate window.
I have also tried doing it locally.
Here are the results:
ROI initialized on [(144, 453), (1381, 440)] Traceback (most recent call last): File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 497, in _import_graph_def_internal graph._c_graph, serialized, options) # pylint: disable=protected-access tensorflow.python.framework.errors_impl.InvalidArgumentError: NodeDef mentions attr 'exponential_avg_factor' not in Op<name=FusedBatchNormV3; signature=x:T, scale:U, offset:U, mean:U, variance:U -> y:T, batch_mean:U, batch_variance:U, reserve_space_1:U, reserve_space_2:U, reserve_space_3:U; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT]; attr=U:type,allowed=[DT_FLOAT]; attr=epsilon:float,default=0.0001; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=is_training:bool,default=true>; NodeDef: {{node FusedBatchNormV3}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.). During handling of the above exception, another exception occurred: Traceback (most recent call last): File "detectvideo_counter.py", line 208, in <module> app.run(main) File "C:\Python37\lib\site-packages\absl\app.py", line 303, in run _run_main(main, args) File "C:\Python37\lib\site-packages\absl\app.py", line 251, in _run_main sys.exit(main(argv)) File "detectvideo_counter.py", line 77, in main saved_model_loaded = tf.saved_model.load(FLAGS.weights, tags=[tag_constants.SERVING]) File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 528, in load return load_internal(export_dir, tags) File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 552, in load_internal export_dir) File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\load.py", line 114, in __init__ meta_graph.graph_def.library)) File "C:\Python37\lib\site-packages\tensorflow_core\python\saved_model\function_deserialization.py", line 312, in load_function_def_library func_graph = function_def_lib.function_def_to_graph(copy) File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\function_def_to_graph.py", line 63, in function_def_to_graph importer.import_graph_def_for_function(graph_def, name="") File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 412, in import_graph_def_for_function graph_def, validate_colocation_constraints=False, name=name) File "C:\Python37\lib\site-packages\tensorflow_core\python\framework\importer.py", line 501, in _import_graph_def_internal raise ValueError(str(e)) ValueError: NodeDef mentions attr 'exponential_avg_factor' not in Op<name=FusedBatchNormV3; signature=x:T, scale:U, offset:U, mean:U, variance:U -> y:T, batch_mean:U, batch_variance:U, reserve_space_1:U, reserve_space_2:U, reserve_space_3:U; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT]; attr=U:type,allowed=[DT_FLOAT]; attr=epsilon:float,default=0.0001; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=is_training:bool,default=true>; NodeDef: {{node FusedBatchNormV3}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
I was able to solve this by installing Tensorflow 2.2.0
I tried to run this command in Colab:
! python detectvideo_counter.py --weights ./checkpoints/yolov4-416/ --size 608 --video {path_video} --score 0.9
This is the result: